Effective face landmark localization via single deep network

In this paper, we propose a novel face alignment method using single deep network (SDN) on existing limited training data. Rather than using a max-pooling layer followed one convolutional layer in typical convolutional neural networks (CNN), SDN adopts a stack of 3 layer groups instead. Each group layer contains two convolutional layers and a max-pooling layer, which can extract the features hierarchically. Moreover, an effective data augmentation strategy and corresponding training skills are also proposed to over-come the lack of training images on COFW and 300-W da-tasets. The experiment results show that our method outper-forms state-of-the-art methods in both detection accuracy and speed.

[1]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[2]  Lizhuang Ma,et al.  Learning deep representation from coarse to fine for face alignment , 2016, ArXiv.

[3]  汤晓鸥.  Deep Convolutional Network Cascade for Facial Point Detection , 2013 .

[4]  Xiaoou Tang,et al.  Learning Deep Representation for Face Alignment with Auxiliary Attributes , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Stefanos Zafeiriou,et al.  300 Faces in-the-Wild Challenge: The First Facial Landmark Localization Challenge , 2013, 2013 IEEE International Conference on Computer Vision Workshops.

[6]  Jian Sun,et al.  Face Alignment by Explicit Shape Regression , 2012, International Journal of Computer Vision.

[7]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[8]  Fernando De la Torre,et al.  Supervised Descent Method and Its Applications to Face Alignment , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Josephine Sullivan,et al.  One millisecond face alignment with an ensemble of regression trees , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Zhenan Sun,et al.  A Lightened CNN for Deep Face Representation , 2015, ArXiv.

[11]  Timothy F. Cootes,et al.  Active Appearance Models , 1998, ECCV.

[12]  Xiaogang Wang,et al.  Deep Convolutional Network Cascade for Facial Point Detection , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Shiguang Shan,et al.  Coarse-to-Fine Auto-Encoder Networks (CFAN) for Real-Time Face Alignment , 2014, ECCV.

[14]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[15]  Qijun Zhao,et al.  Cascaded Regression for 3D Face Alignment , 2016, CCBR.

[16]  Xiaoou Tang,et al.  Facial Landmark Detection by Deep Multi-task Learning , 2014, ECCV.

[17]  Yihong Gong,et al.  Facial landmark detection via cascade multi-channel convolutional neural network , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[18]  Qijun Zhao,et al.  Face Landmark Localization Using a Single Deep Network , 2016, CCBR.

[19]  Thomas S. Huang,et al.  Interactive Facial Feature Localization , 2012, ECCV.

[20]  Pietro Perona,et al.  Robust Face Landmark Estimation under Occlusion , 2013, 2013 IEEE International Conference on Computer Vision.

[21]  Yu Qiao,et al.  Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks , 2016, IEEE Signal Processing Letters.

[22]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[23]  Cheng Li,et al.  Face alignment by coarse-to-fine shape searching , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Feng Liu,et al.  Joint Face Alignment and 3D Face Reconstruction , 2016, ECCV.